{"id":"W2468149677","doi":"10.22215/etd/2012-09696","title":"Exploiting non-uniform query distributions in data structuring problems","year":2012,"lang":"en","type":"dissertation","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; Canadian Heritage; Library and Archives Canada; Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Structuring; Computer science; Information retrieval; Mathematics; Political science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003952296,0.0002316396,0.0002112826,0.0002317737,0.0001281941,0.0004284521,0.003046985,0.0001045042,0.00005212262],"category_scores_gemma":[0.000027151,0.0002175159,0.00003377759,0.0004246828,0.000009691634,0.003875869,0.001129604,0.0002890858,0.00006836696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005860647,"about_ca_system_score_gemma":0.00005794839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000377746,"about_ca_topic_score_gemma":0.001939607,"domain_scores_codex":[0.9982714,0.00001582537,0.0003767397,0.0005995795,0.0002894719,0.0004469994],"domain_scores_gemma":[0.9981422,0.00002910346,0.0001748576,0.001546523,0.000034804,0.00007254198],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008419114,0.0003861288,0.002170101,0.0016845,0.0001787891,0.00006203107,0.003014313,0.00014505,0.0004818634,0.2140161,0.01571281,0.7621399],"study_design_scores_gemma":[0.002417007,0.00009253283,0.124231,0.002990785,0.0002179654,0.00002398361,0.006514188,0.7298541,0.003855425,0.02401059,0.1000887,0.005703641],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01144717,0.0002370851,0.9102355,0.0002111231,0.003260865,0.001000761,0.0004293819,0.0004605909,0.07271757],"genre_scores_gemma":[0.5024781,0.0003368736,0.2831433,0.00009958692,0.001272539,0.0002639591,0.17285,0.000118292,0.03943729],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7564363,"threshold_uncertainty_score":0.8870041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04272130123280293,"score_gpt":0.2829957397456566,"score_spread":0.2402744385128536,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}